Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (102)

Search Parameters:
Keywords = neural radiance field (NeRF)

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
18 pages, 50753 KB  
Article
Closer Nap-of-the-Object Photogrammetry with Geographic Neural Radiance Fields
by Haoyu Liu, Yizhi Zou, Lu Yang, Huifu Chen, Lei Xia and Lubo Li
Drones 2026, 10(7), 524; https://doi.org/10.3390/drones10070524 - 9 Jul 2026
Viewed by 125
Abstract
High-precision 3D reconstruction of objects with complex surfaces, such as ancient architecture and detailed artworks, requires close-range image acquisition, which remains challenging for Unmanned Aerial Vehicle (UAV) systems. The operational proximity of current UAV workflows is often insufficient to capture fine geometric and [...] Read more.
High-precision 3D reconstruction of objects with complex surfaces, such as ancient architecture and detailed artworks, requires close-range image acquisition, which remains challenging for Unmanned Aerial Vehicle (UAV) systems. The operational proximity of current UAV workflows is often insufficient to capture fine geometric and textural details, limiting high-fidelity digitization. This paper presents a georeferenced NeRF-based UAV acquisition framework for automated waypoint planning and supervised close-proximity execution. The core of the framework is a path-planning module that operates on a metric geometric prior established through Geographic Neural Radiance Fields (Geo-NeRF), which denotes a georeferenced NeRF modeling pipeline rather than a new NeRF architecture or loss function. By generating waypoints directly on this neural representation and optimizing the flight path via a nearest-neighbor strategy, the proposed framework supports close-proximity image acquisition for static targets under controlled conditions. Empirical validation demonstrates improved close-range flight proximity, photographic accuracy, and 3D reconstruction fidelity compared with the evaluated baselines. Full article
(This article belongs to the Topic 3D Documentation of Natural and Cultural Heritage)
Show Figures

Figure 1

24 pages, 5888 KB  
Article
NeRF-Based Three-Dimensional Reconstruction for Large-Diameter Rescue Shafts
by Hairong Gu, Jiaxi Wang, Chenggang Chen, Wenjuan Yang, Mostak Ahamed and Zujie Zou
Sensors 2026, 26(12), 3847; https://doi.org/10.3390/s26123847 - 17 Jun 2026
Viewed by 207
Abstract
Large-diameter rescue shafts serve as critical infrastructure for emergency response in mining disaster scenarios, and their structural deformation directly affects the safe passage of rescue capsules. In this paper, we investigate three-dimensional (3D) reconstruction techniques for large-diameter rescue shaft environments and develop a [...] Read more.
Large-diameter rescue shafts serve as critical infrastructure for emergency response in mining disaster scenarios, and their structural deformation directly affects the safe passage of rescue capsules. In this paper, we investigate three-dimensional (3D) reconstruction techniques for large-diameter rescue shaft environments and develop a Neural Radiance Fields (NeRF)-based reconstruction and deformation assessment scheme. The proposed workflow integrates no reference signal-to-noise-ratio (NR-SNR), image-quality filtering, SfM-based camera-pose estimation, Nerfacto reconstruction, point-cloud export, and circular-section fitting. The NR-SNR retention-ratio experiment shows that retaining approximately 35% high-quality images provides a practical efficiency–quality trade-off for the present dataset, reducing the computational burden of SfM pose estimation while preserving sufficient geometric information for subsequent reconstruction. The reconstructed radiance field is further exported as a dense point cloud and evaluated using relative radius error, circle-fitting residuals, and image-level rendering metrics. Experiments on a simulated large-diameter rescue shaft platform show that the proposed NeRF-based scheme provides favorable geometric measurement applicability and visual reconstruction quality under weak-texture and low-illumination conditions. Compared with conventional MVS and the tested 3DGS baseline, the proposed scheme produces a point-cloud output that is more suitable for subsequent circular-section fitting and deformation-related assessment. In addition, comparison with a representative SDF-based baseline indicates that direct implicit surface recovery remains challenging for the tested hollow cylindrical shaft-wall scene. The results demonstrate the potential of the proposed NeRF-based workflow for rescue-shaft inner-wall reconstruction and engineering-oriented deformation evaluation. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

22 pages, 249676 KB  
Article
AI- and AR-Assisted Reactivation of Chinese Paper Cutting Using Temple Arts and Ancient Paintings
by Naai-Jung Shih and Yan-Ting Chen
Heritage 2026, 9(4), 150; https://doi.org/10.3390/heritage9040150 - 7 Apr 2026
Cited by 1 | Viewed by 1360
Abstract
Traditional Chinese paper cutting represents an important intangible cultural heritage. Can artificial intelligence (AI) reactivate the heritage in a new style? The aim of this study was to use AI to reactivate temple arts and paintings by converting them into the style of [...] Read more.
Traditional Chinese paper cutting represents an important intangible cultural heritage. Can artificial intelligence (AI) reactivate the heritage in a new style? The aim of this study was to use AI to reactivate temple arts and paintings by converting them into the style of traditional Chinese paper cuttings. Thirty sets of old images taken 18 years ago and 10 images of ancient paintings from the National Palace Museum were restyled in Nano Banana (Pro)®. Related design elements included integrated isolated parts, visual depth, details, and solid and void alternation. Three-dimensional stone and wood sculptures were reconstructed using Rodin® or Meshy® and converted into AR models in Sketchfab®. From the generated 2D images and their 3D representations, a reactivated style of Chinese paper cutting was developed that can be interacted with in the AR smartphone platform or RP in the physical world. Approximately 370 images were regenerated, and 167 versions of models were reconstructed. AI should be considered part of culture. Rethinking traditional folk art highlights demand for the cross-reference and cross-reactivation of heterogeneous art forms. This AI model interprets novel 3D structural and visual details and creates a unique 2D and 3D identity for each subject. Full article
Show Figures

Figure 1

29 pages, 7604 KB  
Article
Shading and Geometric Constraint Neural Radiance Field for DSM Reconstruction from Multi-View Satellite Images
by Zhihua Hu, Zhiwen Chen, Yushun Li, Yuxuan Liu, Kao Zhang, Chenguang Zhao and Yongxian Zhang
Remote Sens. 2026, 18(7), 1091; https://doi.org/10.3390/rs18071091 - 5 Apr 2026
Viewed by 547
Abstract
With the continued development of spatial information technologies, Digital Surface Models (DSMs) have become fundamental data products for urban planning, virtual reality, geographic information systems, and digital-earth applications. Neural Radiance Fields (NeRFs) have achieved remarkable success in multi-view 3D reconstruction in computer vision. [...] Read more.
With the continued development of spatial information technologies, Digital Surface Models (DSMs) have become fundamental data products for urban planning, virtual reality, geographic information systems, and digital-earth applications. Neural Radiance Fields (NeRFs) have achieved remarkable success in multi-view 3D reconstruction in computer vision. Still, their application to DSM generation from satellite imagery remains challenging because of differences in imaging geometry, complex surface structure, and varying illumination conditions. To address these issues, this paper proposes a Shading and Geometric Constraint (SGC) method tailored to satellite photogrammetry and designed to integrate with existing NeRF-based frameworks such as Sat-NeRF and EO-NeRF. First, a physical imaging model based on Lambertian reflectance and spherical harmonics is introduced to represent the complex illumination variations in satellite images. Synthetic images generated by this model provide auxiliary supervision that improves robustness to illumination inconsistency. Second, inspired by classical shading-based refinement methods, we introduce a bilateral edge-preserving geometric constraint. Unlike standard smoothness terms, this constraint uses photometric discrepancies to weight geometric smoothing, thereby preserving sharp building boundaries while smoothing flat surfaces. We integrate the method into two state-of-the-art baselines, Sat-NeRF and EO-NeRF. EO-NeRF+SGC achieves up to a 57.93% reduction in elevation MAE relative to EO-NeRF, which is the largest relative MAE reduction reported in this study. The method also recovers finer structural details and sharper edges than recently published NeRF-based DSM reconstruction methods. Full article
Show Figures

Figure 1

47 pages, 8613 KB  
Review
2D-to-3D Image Reconstruction in Agriculture: A Review of Methods, Challenges, and AI-Driven Opportunities
by Hemanth Reddy Sankaramaddi, Won Suk Lee, Kyoungchul Kim and Youngki Hong
Sensors 2026, 26(6), 1775; https://doi.org/10.3390/s26061775 - 11 Mar 2026
Cited by 1 | Viewed by 2371
Abstract
Agriculture is rapidly becoming a data-driven field where automation relies on transforming 2D images into accurate 3D models. However, selecting the most effective method remains challenging due to the unconstrained nature of the environment. This review assesses the effectiveness of geometry-based, sensor-based, and [...] Read more.
Agriculture is rapidly becoming a data-driven field where automation relies on transforming 2D images into accurate 3D models. However, selecting the most effective method remains challenging due to the unconstrained nature of the environment. This review assesses the effectiveness of geometry-based, sensor-based, and learning-based reconstruction methodologies in agricultural settings. We analyze photogrammetric pipelines, active sensing, and neural rendering methods based on their geometric accuracy, data processing speed, and field performance against wind or occlusion. Our analysis indicates that while Light Detection and Ranging (LiDAR) is highly accurate, it is too expensive for widespread adoption. Conversely, geometry-based methods are inexpensive but struggle with complex biological structures. Learning-based methods, especially 3D Gaussian Splatting (3DGS), have revolutionized the field by enabling a balance between visual fidelity and real-time inference speed. We conclude that the best chance for scalability and accuracy lies in hybrid pipelines that integrate Vision Foundation Models (VFMs) with geometric priors. We believe that “hybrid intelligence” systems, such as edge-native 3D Gaussian Splatting combined with semantic priors, are the future of 3D reconstruction. These systems will enable the creation of real-time, spatiotemporal (4D) digital twins that drive automated decision-making in precision agriculture. Full article
(This article belongs to the Special Issue Feature Papers in Smart Agriculture 2025)
Show Figures

Figure 1

21 pages, 1926 KB  
Article
From 2D to 3D: A Generative Model from Single Image to Digital 3D of Chinese Three Gorges Cultural Relics
by Guang Wu, Mingyuan Ge, Yunxiang Wang, Youhao Chen and Li Liu
Appl. Sci. 2026, 16(6), 2678; https://doi.org/10.3390/app16062678 - 11 Mar 2026
Viewed by 1052
Abstract
The acquisition of high-quality three-dimensional (3D) models of cultural relics often relies on expensive scanning equipment or multi-view image capture, which limits large-scale deployment in real-world heritage conservation scenarios. Large-scale water impoundment in the Three Gorges region has resulted in the permanent submergence [...] Read more.
The acquisition of high-quality three-dimensional (3D) models of cultural relics often relies on expensive scanning equipment or multi-view image capture, which limits large-scale deployment in real-world heritage conservation scenarios. Large-scale water impoundment in the Three Gorges region has resulted in the permanent submergence of numerous cultural relics and archaeological remains. For many of these artifacts, only a single two-dimensional image remains as the sole visual record, posing significant challenges for reconstructing their original three-dimensional geometry and appearance. This limitation renders traditional multi-view reconstruction and physical scanning methods infeasible. To address this challenge, we propose a generative framework for reconstructing high-fidelity 3D digital models of Chinese Three Gorges cultural relics from a single two-dimensional (2D) image. Building upon recent advances in generative 3D representation learning, the proposed method adopts a transformer-based image-to-triplane architecture to infer an implicit 3D representation directly from a single RGB image. A vision transformer encoder is employed to extract global and local visual features, which are subsequently projected into a compact triplane representation through a cross-attention-based decoder. The reconstructed triplane features are further decoded by a neural radiance field (NeRF) to synthesize dense geometry and appearance, enabling accurate mesh extraction and novel-view rendering. To enhance robustness under in-the-wild conditions, the model implicitly estimates camera parameters during inference without relying on explicit calibration information. The proposed method is evaluated on a dataset of Chinese Three Gorges cultural relics, covering diverse artifact categories and visual styles. Experimental results demonstrate that the proposed framework is capable of producing structurally coherent and visually consistent 3D reconstructions from a single image, effectively preserving key morphological characteristics of cultural relics under limited data conditions. Compared with existing single-image and multi-view reconstruction baselines, the proposed framework exhibits better reconstruction accuracy, visual consistency, and generalization capability. This study provides an efficient and scalable solution for the digital reconstruction of cultural relics and offers a practical pathway for large-scale 3D digitization of heritage artifacts from archival images. This work provides a practical solution for the digital reconstruction of submerged heritage artifacts and contributes to the application of generative 3D modeling techniques in cultural heritage preservation and restoration. Full article
Show Figures

Figure 1

21 pages, 2176 KB  
Article
Complex Illumination-Aware 3D Gaussian Reconstruction for Uncooperative Space Objects
by Ziang Qu, Zhang Zhang, Ruiqi Xun, Junlan Zhou and Liang Chang
Aerospace 2026, 13(3), 258; https://doi.org/10.3390/aerospace13030258 - 10 Mar 2026
Viewed by 613
Abstract
High-precision 3D reconstruction of non-cooperative space targets is a critical technology for on-orbit servicing (OOS) and situational awareness, driven by the growing number of OOS missions. However, traditional visual algorithms struggle to acquire accurate geometric information due to the unique high-dynamic-range lighting and [...] Read more.
High-precision 3D reconstruction of non-cooperative space targets is a critical technology for on-orbit servicing (OOS) and situational awareness, driven by the growing number of OOS missions. However, traditional visual algorithms struggle to acquire accurate geometric information due to the unique high-dynamic-range lighting and strong specular reflections characteristic of the space environment. This paper proposes Space-Gaussian, a compact 3D Gaussian reconstruction method tailored for complex lighting environments. Built upon the 3D Gaussian Splatting (3DGS) framework, the method incorporates a physically based rendering pipeline and a microfacet bidirectional reflectance distribution function model. By decoupling geometric structure from material properties and utilizing deferred rendering, it effectively suppresses geometric artifacts and specular highlights arising from non-Lambertian surface reflections. Comparative experiments on a high-fidelity simulation dataset demonstrate that Space-Gaussian outperforms mainstream methods—including Neural Radiance Fields (NeRF), Instant-NGP, GaussianShader, and 3DGS—in geometric reconstruction accuracy, novel view synthesis quality, and real-time rendering. On our self-created dataset, our approach achieves a significant performance boost over existing 3DGS methods. The results highlight its potential for high-fidelity, real-time 3D perception on resource-constrained spacecraft platforms. Full article
(This article belongs to the Section Astronautics & Space Science)
Show Figures

Figure 1

27 pages, 4167 KB  
Article
OptiNeRF: A Spatially Optimized Neural Rendering Framework for Complex Scene Reconstruction
by Xinyuan Gu, Yanbo Chang, Junyue Xia, Yue Yu, Zhen Tian and Junming Chen
Mathematics 2026, 14(5), 842; https://doi.org/10.3390/math14050842 - 1 Mar 2026
Viewed by 666
Abstract
Neural rendering techniques aim to generate photorealistic images and accurate 3D geometries from multi-view images but often struggle with efficiency and geometric consistency in complex or dynamic scenes. Optimized Neural Radiance Fields (OptiNeRF) addresses these challenges through several innovations. It uses spatially optimized [...] Read more.
Neural rendering techniques aim to generate photorealistic images and accurate 3D geometries from multi-view images but often struggle with efficiency and geometric consistency in complex or dynamic scenes. Optimized Neural Radiance Fields (OptiNeRF) addresses these challenges through several innovations. It uses spatially optimized sampling to focus on points near object surfaces, reducing computation while improving precision. Leveraging the pre-trained Marigold model, it generates depth and normal maps as geometric priors. Sampled points are processed through a hybrid network combining an MLP and a multi-resolution feature grid (MRF), capturing fine details and large-scale structures. To handle varying illumination and complex materials, OptiNeRF introduces adaptive volume rendering (AVR), dynamically adjusting light transparency and scattering. A progressive sampling strategy further focuses computation on regions with high geometric complexity. The loss function incorporates RGB, normal, depth, boundary, and lighting optimization losses, with adaptive weight modulation for geometric priors, ensuring both visual fidelity and geometric consistency even with inaccurate depth/normal estimates. Experiments on dynamic scenes show strong performance, with a PSNR of 32.10 dB, SSIM of 0.936, Chamfer distance of 1.28 × 10−3, training time of 12 h, and rendering speed of 25 FPS, demonstrating high geometric accuracy, realistic rendering, and computational efficiency over conventional methods. Full article
(This article belongs to the Special Issue Intelligent Mathematics and Applications)
Show Figures

Figure 1

19 pages, 20762 KB  
Article
Asymmetric Explicit Synergy for Multi-Modal 3D Gaussian Pre-Training in Autonomous Driving
by Dingwei Zhang, Jie Ji, Chengjun Huang, Bichun Li, Chennian Yu, Chenhui Qu, Zhengyuan Yang, Chen Hua and Biao Yu
World Electr. Veh. J. 2026, 17(2), 102; https://doi.org/10.3390/wevj17020102 - 19 Feb 2026
Viewed by 1095
Abstract
Generative pre-training via neural rendering has become a cornerstone for scaling 3D perception in autonomous driving. However, prevalent approaches relying on implicit Neural Radiance Fields (NeRFs) face two fundamental limitations: the shape-radiance ambiguity inherent in vision-centric optimization and the prohibitive computational overhead of [...] Read more.
Generative pre-training via neural rendering has become a cornerstone for scaling 3D perception in autonomous driving. However, prevalent approaches relying on implicit Neural Radiance Fields (NeRFs) face two fundamental limitations: the shape-radiance ambiguity inherent in vision-centric optimization and the prohibitive computational overhead of volumetric ray marching. To address these challenges, we propose AES-Gaussian, a novel multi-modal pre-training framework grounded in the efficient 3D Gaussian Splatting (3DGS) representation. Diverging from symmetric fusion paradigms, our core innovation is an Asymmetric Encoder architecture that couples a deep semantic vision backbone with a lightweight, physics-aware LiDAR branch. In this framework, LiDAR data serve not merely for semantic extraction, but as sparse physical anchors. By employing a novel Explicit Feature Synergy mechanism, we directly inject raw LiDAR intensity and depth priors into the Gaussian decoding process, thereby rigidly constraining scene geometry in open-world environments. Extensive empirical validation on the nuScenes dataset demonstrates the superiority of our approach. AES-Gaussian achieves state-of-the-art transfer performance, yielding a substantial 7.0% improvement in NDS for 3D Object Detection and a 4.8% mIoU gain in 3D semantic occupancy prediction compared to baselines. Notably, our method reduces geometric reconstruction error by over 50% while significantly improving training and inference efficiency, attributed to the streamlined asymmetric design and rapid Gaussian rasterization. Ultimately, by enhancing both perception accuracy and system efficiency, this work contributes to the development of safer and more reliable autonomous driving systems. Full article
(This article belongs to the Section Automated and Connected Vehicles)
Show Figures

Figure 1

24 pages, 7887 KB  
Article
A Novel Multi-Cooperative Neural Radiance Field Reconstruction Method Based on Optical Properties for 3D Reconstruction of Scenes Containing Transparent Objects
by Xiaopeng Sha, Wenbo Sun, Kai Sun, Xinqi Sang and Shuyu Wang
Symmetry 2026, 18(2), 371; https://doi.org/10.3390/sym18020371 - 17 Feb 2026
Viewed by 1620
Abstract
Due to phenomena, such as refraction, reflection, and light scattering, the three-dimensional (3D) reconstruction of transparent objects with complex geometric symmetry or contours is confronted with the challenges of insufficient extraction of feature points and recognition of contour detail. To solve this challenge, [...] Read more.
Due to phenomena, such as refraction, reflection, and light scattering, the three-dimensional (3D) reconstruction of transparent objects with complex geometric symmetry or contours is confronted with the challenges of insufficient extraction of feature points and recognition of contour detail. To solve this challenge, a novel reconstruction method based on multi-cooperative Neural Radiance Fields (NeRF) is proposed in the paper. This method incorporates angular offset fields and local reconstruction fields, explicitly modeling the effects of refraction and reflection during light propagation. The angular offset field simulates the internal refractive deflection within transparent materials, while the localized reconstruction field performs secondary reconstruction in regions affected by specular reflection. This approach effectively captures surface contours of transparent objects and accurately reconstructs scene details. Experimental results demonstrate that our method achieves approximately 10% improvement in reconstruction accuracy compared to traditional neural radiance field techniques, with a PSNR of 25, an increased SSIM of 0.87, and a reduced LPIPS value of 0.365. The proposed method offers a new perspective for reconstructing transparent objects and scenes containing such materials, holding significant theoretical and practical value. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

22 pages, 5296 KB  
Article
Pepper-4D: Spatiotemporal 3D Pepper Crop Dataset for Phenotyping
by Foysal Ahmed, Dawei Li, Boyuan Zhao, Zhanjiang Wang, Jiali Huang, Tingzhicheng Li, Jingjing Huang, Jiahui Hou, Sayed Jobaer and Han Yan
Plants 2026, 15(4), 599; https://doi.org/10.3390/plants15040599 - 13 Feb 2026
Cited by 1 | Viewed by 1352
Abstract
Pepper (Capsicum annuum) is a globally significant horticultural crop cultivated for its culinary, medicinal, and economic value. Traditional approaches for boosting the agricultural production of pepper, notably, expanding farmland, have become increasingly unsustainable. Recent advancements in artificial intelligence and 3D computer [...] Read more.
Pepper (Capsicum annuum) is a globally significant horticultural crop cultivated for its culinary, medicinal, and economic value. Traditional approaches for boosting the agricultural production of pepper, notably, expanding farmland, have become increasingly unsustainable. Recent advancements in artificial intelligence and 3D computer vision have started to transform crop cultivation and phenotyping, which has shed new light on increasing production by advanced breeding. However, currently, the field still lacks 3D pepper data that contains enough detail for organ-level analysis. Therefore, we propose Pepper-4D, a new, high-precision 4D point cloud dataset that records both the spatial structure and temporal development of pepper plants across various continuous growth stages. Our dataset is divided into three subsets, including a total of 916 individual point clouds from 29 indoor-cultivated pepper plant samples. Our dataset provides manual annotations at both the plant-level and organ-level, supporting phenotyping tasks such as pepper growth status classification, organ semantic segmentation, organ instance segmentation, organ growth tracking, new organ detection, and even the generation of synthetic 3D pepper plants. Full article
(This article belongs to the Special Issue AI-Driven Machine Vision Technologies in Plant Science)
Show Figures

Graphical abstract

19 pages, 3074 KB  
Article
Enhancing Audio–Visual Synchronization and Spatiotemporal Expressiveness for Talking Face Generation
by Tao Wen, Hengjie Lu, Yuan Gao and Shugong Xu
Appl. Sci. 2026, 16(4), 1720; https://doi.org/10.3390/app16041720 - 9 Feb 2026
Viewed by 857
Abstract
Talking face generation aims to produce high-fidelity, temporally coherent videos of speakers with synchronized lip movements aligned to input audio. neural radiance fields (NeRF) are widely adopted due to their realistic modeling capabilities. However, existing NeRF-based approaches face several challenges. First, background noise [...] Read more.
Talking face generation aims to produce high-fidelity, temporally coherent videos of speakers with synchronized lip movements aligned to input audio. neural radiance fields (NeRF) are widely adopted due to their realistic modeling capabilities. However, existing NeRF-based approaches face several challenges. First, background noise often disrupts lip synchronization, making it difficult to align lip movements accurately with audio signals, especially when training data are temporally constrained. Furthermore, these methods suffer from spatiotemporal inconsistency, which manifests in two ways: temporally, unreliable audio signals lead to flickering lip movements, undermining coherence; spatially, the lack of facial structure constraints reduces realism and hinders training efficiency. To address these issues, we propose a NeRF-based method that enhances audio–visual synchronization and SpatioTemporal expressiveness for talking face generation (AVIST). Specifically, we enhance the saliency of human speech in audio using audio event features, effectively suppressing background noise interference during training and inference to improve lip-sync accuracy. Additionally, we introduce a feedback mechanism that incorporates lip features from preceding frames to stabilize current lip movements, mitigating temporal instability. Finally, we integrate facial depth supervision to expedite network training and enhance spatial consistency, resulting in more realistic face rendering. Extensive experiments on mainstream datasets demonstrate that AVIST achieves state-of-the-art performance in lip synchronization, spatiotemporal stability, and overall visual fidelity. Full article
Show Figures

Figure 1

20 pages, 2389 KB  
Article
A Monocular Depth Estimation Method for Autonomous Driving Vehicles Based on Gaussian Neural Radiance Fields
by Ziqin Nie, Zhouxing Zhao, Jieying Pan, Yilong Ren, Haiyang Yu and Liang Xu
Sensors 2026, 26(3), 896; https://doi.org/10.3390/s26030896 - 29 Jan 2026
Viewed by 973
Abstract
Monocular depth estimation is one of the key tasks in autonomous driving, which derives depth information of the scene from a single image. And it is a fundamental component for vehicle decision-making and perception. However, approaches currently face challenges such as visual artifacts, [...] Read more.
Monocular depth estimation is one of the key tasks in autonomous driving, which derives depth information of the scene from a single image. And it is a fundamental component for vehicle decision-making and perception. However, approaches currently face challenges such as visual artifacts, scale ambiguity and occlusion handling. These limitations lead to suboptimal performance in complex environments, reducing model efficiency and generalization and hindering their broader use in autonomous driving and other applications. To solve these challenges, this paper introduces a Neural Radiance Field (NeRF)-based monocular depth estimation method for autonomous driving. It introduces a Gaussian probability-based ray sampling strategy to effectively solve the problem of massive sampling points in large complex scenes and reduce computational costs. To improve generalization, a lightweight spherical network incorporating a fine-grained adaptive channel attention mechanism is designed to capture detailed pixel-level features. These features are subsequently mapped to 3D spatial sampling locations, resulting in diverse and expressive point representations for improving the generalizability of the NeRF model. Our approach exhibits remarkable performance on the KITTI benchmark, surpassing traditional methods in depth estimation tasks. This work contributes significant technical advancements for practical monocular depth estimation in autonomous driving applications. Full article
Show Figures

Figure 1

25 pages, 14250 KB  
Article
AI-Based 3D Modeling Strategies for Civil Infrastructure: Quantitative Assessment of NeRF and Photogrammetry
by Edison Atencio, Fabrizzio Duarte, Fidel Lozano-Galant, Rocio Porras and Ye Xia
Sensors 2026, 26(3), 852; https://doi.org/10.3390/s26030852 - 28 Jan 2026
Viewed by 1283
Abstract
Three-dimensional (3D) modeling technologies are increasingly vital in civil engineering, providing precise digital representations of infrastructure for analysis, supervision, and planning. This study presents a comparative assessment of Neural Radiance Fields (NeRFs) and digital photogrammetry using a real-world case study involving a terrace [...] Read more.
Three-dimensional (3D) modeling technologies are increasingly vital in civil engineering, providing precise digital representations of infrastructure for analysis, supervision, and planning. This study presents a comparative assessment of Neural Radiance Fields (NeRFs) and digital photogrammetry using a real-world case study involving a terrace at the Civil Engineering School of the Pontificia Universidad Católica de Valparaíso. The comparison is motivated by the operational complexity of image acquisition campaigns, where large image datasets increase flight time, fieldwork effort, and survey costs. Both techniques were evaluated across varying levels of data availability to analyze reconstruction behavior under progressively constrained image acquisition conditions, rather than to propose new algorithms. NeRF and photogrammetry were compared based on visual quality, point cloud density, geometric accuracy, and processing time. Results indicate that NeRF delivers fast, photorealistic outputs even with reduced image input, enabling efficient coverage with fewer images, while photogrammetry remains superior in metric accuracy and structural completeness. The study concludes by proposing an application-oriented evaluation framework and potential hybrid workflows to guide the selection of 3D modeling technologies based on specific engineering objectives, survey design constraints, and resource availability while also highlighting how AI-based reconstruction methods can support emerging digital workflows in infrastructure monitoring under variable or limited data conditions. Full article
(This article belongs to the Special Issue AI-Enabled Smart Sensors for Industry Monitoring and Fault Diagnosis)
Show Figures

Figure 1

20 pages, 13461 KB  
Article
Multi-View 3D Reconstruction of Ship Hull via Multi-Scale Weighted Neural Radiation Field
by Han Chen, Xuanhe Chu, Ming Li, Yancheng Liu, Jingchun Zhou, Xianping Fu, Siyuan Liu and Fei Yu
J. Mar. Sci. Eng. 2026, 14(2), 229; https://doi.org/10.3390/jmse14020229 - 21 Jan 2026
Viewed by 888
Abstract
The 3D reconstruction of vessel hulls is crucial for enhancing safety, efficiency, and knowledge in the maritime industry. Neural Radiance Fields (NeRFs) are an alternative to 3D reconstruction and rendering from multi-view images; particularly, tensor-based methods have proven effective in improving efficiency. However, [...] Read more.
The 3D reconstruction of vessel hulls is crucial for enhancing safety, efficiency, and knowledge in the maritime industry. Neural Radiance Fields (NeRFs) are an alternative to 3D reconstruction and rendering from multi-view images; particularly, tensor-based methods have proven effective in improving efficiency. However, existing tensor-based methods typically suffer from a lack of spatial coherence, resulting in gaps in the reconstruction of fine-grained geometric structures. This paper proposes a spatial multi-scale weighted NeRF (MDW-NeRF) for accurate and efficient surface reconstruction of vessel hulls. The proposed method develops a novel multi-scale feature decomposition mechanism that models 3D space by leveraging multi-resolution features, facilitating the integration of high-resolution details with low-resolution regional information. We designed separate color and density weighting, using a coarse-to-fine strategy, for density and a weighted matrix for color to decouple feature vectors from appearance attributes. To boost the efficiency of 3D reconstruction and rendering, we implement a hybrid sampling point strategy for volume rendering, selecting sample points based on volumetric density. Extensive experiments on the SVH dataset confirm MDW-NeRF’s superiority: quantitatively, it outperforms TensoRF by 1.5 dB in PSNR and 6.1% in CD, and shrinks the model size by 9%, with comparable training times; qualitatively, it resolves tensor-based methods’ inherent spatial incoherence and fine-grained gaps, enabling accurate restoration of hull cavities and realistic surface texture rendering. These results validate our method’s effectiveness in achieving excellent rendering quality, high reconstruction accuracy, and timeliness. Full article
Show Figures

Figure 1

Back to TopTop